deltasignal-atlas-7

deltasignal-atlas-7 is a skill for Claude Code, Codex from aitrailblazer/deltasignal-atlas-codex-plugin. It costs 81 tokens per session (4,402 once invoked), scanned A, original, MIT.

A research skill for checking public cryptocurrency companies against filings submitted to the U.S. Securities and Exchange Commission (SEC). It covers company finances, debt obligations, stress signals, peer comparisons, and audit status.

In plain words
What is it for?
Use it to monitor crypto-related public companies, identify issuers under the most financial stress, review fundamentals and debt terms, rank peers, and inspect supporting evidence.
Why use it?
It brings related SEC-based company information into a structured view, reducing the need to gather and compare filings manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Good fit Use it to monitor crypto-related public companies, identify issuers under the most financial stress, review fundamentals and debt terms, rank peers, and inspect supporting evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aitrailblazer/deltasignal-atlas-codex-plugin/deltasignal-atlas
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add aitrailblazer/deltasignal-atlas-codex-plugin --skill deltasignal-atlas
Clone the repo
git clone --depth 1 https://github.com/aitrailblazer/deltasignal-atlas-codex-plugin

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deltasignal-atlas-7

README.md
[![agentmods](https://agentmods.dev/badge/skills/aitrailblazer/deltasignal-atlas-codex-plugin/deltasignal-atlas/github.svg)](https://agentmods.dev/skills/aitrailblazer/deltasignal-atlas-codex-plugin/deltasignal-atlas)
Your own site
<a href="https://agentmods.dev/skills/aitrailblazer/deltasignal-atlas-codex-plugin/deltasignal-atlas"><img src="https://agentmods.dev/badge/skills/aitrailblazer/deltasignal-atlas-codex-plugin/deltasignal-atlas/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deltasignal-atlas-7

Your own site · 80×15
<a href="https://agentmods.dev/skills/aitrailblazer/deltasignal-atlas-codex-plugin/deltasignal-atlas"><img src="https://agentmods.dev/badge/skills/aitrailblazer/deltasignal-atlas-codex-plugin/deltasignal-atlas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.04402
Opus 5 $0.00041 $0.02201
Sonnet 5 $0.00016 $0.00880
Haiku 4.5 $0.00008 $0.00440

Measured 12d ago against content hash ead4b23ce482, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

deltasignal-atlas-7 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/deltasignal-atlas/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeltaSignal ATLAS-7

Use this skill when the user asks for DeltaSignal, ATLAS-7, crypto public issuer stress, SEC-grounded crypto equity intelligence, covenant stress, top-stressed issuers, issuer fundamentals, or DeltaSignal paid API access.

Access Model

DeltaSignal is a usage-based intelligence API with a free starter tier. Do not imply there is a subscription requirement.

Free tier:

  • The Base x402 /v1/* routes allow 5 free calls per user before payment fallback.
  • If the free tier is exhausted, the same route returns x402 payment requirements for compatible clients.
  • If a caller includes an x402 payment header, treat it as an intentional paid request rather than consuming free quota.

Primary rail:

  • Tempo MPP routes under https://api.aitrailblazer.net/mpp/v1/*

Agentic Market compatibility rail:

  • Base x402 routes under https://api.aitrailblazer.net/v1/*
  • Base network: eip155:8453
  • Payment asset: USDC

Bundled MCP server:

  • Treat DeltaSignal as an MCP-first plugin. Prefer named MCP tool calls over hand-written HTTP routes whenever the plugin is installed.
  • Public MCP initialize and tools/list are free discovery methods. Public MCP tools/call remains protected by x402 payment unless a free-tier grant applies.
  • Prefer composite MCP presets for common workflows:
    • deltasignal_morning_brief for daily scans.
    • deltasignal_company_report for full ticker reports.
    • deltasignal_pressure_board for risk monitoring.
    • deltasignal_alpha_sweep for opportunity screening.
    • deltasignal_quick_ticker_check for fast ticker checks.
    • deltasignal_daily_changes for compact Daily Monitoring.
    • deltasignal_daily_change_evidence for explicit issuer proof after a monitoring result.
    • deltasignal_atlas7_audit_status for operator checks that the Azure-native 215-issuer regression audit is healthy and fresh.
  • Use granular tools only for custom drilldowns or when a composite preset is unavailable.
  • Prefer the deltasignal_* MCP tools when this plugin is installed and the request maps to a supported DeltaSignal route.
  • MCP tools are read-only, idempotent, closed-world tools with strict argument validation.
  • In live mode, the MCP wrapper calls the deployed Base x402 /v1/* routes and returns free-tier headers or x402 payment requirements in the tool result.
  • In internal mode, the MCP wrapper uses a pre-authorized DELTASIGNAL_API_KEY against the deployed API for no-payment smoke testing.
  • In local mode, the MCP wrapper calls http://127.0.0.1:8080/v1/* without x402 payment so DeltaSignal can be used during development work.
  • If the MCP wrapper returns payment_required, do not claim payment succeeded. Tell the user the free tier is exhausted or unavailable and switch to an x402/MPP-capable payment flow.

Read the full file on GitHub · 185 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 185 lines · 81 tokens per session scan A ead4b23ce482

Subscribe to this mod's changes

deltasignal-atlas-7 is a skill published in the GitHub repository aitrailblazer/deltasignal-atlas-codex-plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 4,402 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.